多源多智能体证据检索用于事实核查
Multi-Sourced, Multi-Agent Evidence Retrieval for Fact-Checking
AI总结：
WKGFC通过多智能体证据检索和知识图谱增强，提升事实核查的准确性和鲁棒性。
摘要：
互联网上的虚假信息传播对社会和个人都构成了重大威胁，需要具有鲁棒性和可扩展性的事实核查方法，该方法依赖于检索准确且可信的证据。以往的方法依赖于从训练数据中学习的语义和社会上下文模式，这限制了它们对新数据分布的泛化能力。最近，基于检索增强生成（RAG）的方法被提出，利用LLM的推理能力与检索到的 grounding 文档进行结合。然而，这些方法主要依赖于文本相似性进行证据检索，并且在处理丰富文档内容中的多跳语义关系时存在困难。这些局限性导致在证据检索过程中忽略了待核查声明与证据之间的微妙事实关联，从而导致不准确的真伪预测。为了解决这些问题，我们提出了WKGFC，它利用授权的开放知识图谱作为证据的核心资源。LLM启用的检索被设计用来评估声明并检索最相关的知识子图，形成结构化的证据用于事实验证。为了增强知识图谱证据，我们检索网络内容以进行补充。上述过程被实现为一个自动的马尔可夫决策过程（MDP）：一个推理LLM智能体根据当前证据和声明决定采取什么行动。为了将MDP适应于事实核查，我们使用提示优化来微调智能体LLM。
英文摘要：
Misinformation spreading over the Internet poses a significant threat to both societies and individuals, necessitating robust and scalable fact-checking that relies on retrieving accurate and trustworthy evidence. Previous methods rely on semantic and social-contextual patterns learned from training data, which limits their generalization to new data distributions. Recently, Retrieval Augmented Generation (RAG) based methods have been proposed to utilize the reasoning capability of LLMs with retrieved grounding evidence documents. However, these methods largely rely on textual similarity for evidence retrieval and struggle to retrieve evidence that captures multi-hop semantic relations within rich document contents. These limitations lead to overlooking subtle factual correlations between the evidence and the claims to be fact-checked during evidence retrieval, thus causing inaccurate veracity predictions. To address these issues, we propose WKGFC, which exploits authorized open knowledge graph as a core resource of evidence. LLM-enabled retrieval is designed to assess the claims and retrieve the most relevant knowledge subgraphs, forming structured evidence for fact verification. To augment the knowledge graph evidence, we retrieve web contents for completion. The above process is implemented as an automatic Markov Decision Process (MDP): A reasoning LLM agent decides what actions to take according to the current evidence and the claims. To adapt the MDP for fact-checking, we use prompt optimization to fine-tune the agentic LLM.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
